GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA

Emma Izquierdo-Verdiguier; Álvaro Moreno-Martínez; Jose E. Adsuara; Jordi Muñoz-Marí; Gustau Camps-Valls; Marco P. Maneta; John Kimball; Nicholas Clinton; Steven W. Running

doi:10.1109/IGARSS47720.2021.9554790

GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA

Emma Izquierdo-Verdiguier
, Álvaro Moreno-Martínez
, Jose E. Adsuara
, Jordi Muñoz-Marí
, Gustau Camps-Valls
, Marco P. Maneta
, John Kimball
, Nicholas Clinton
, Steven W. Running

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

Image classification has become one of the most common applications in remote sensing yielding to the creation of a variety of operational thematic maps at multiple spatio-temporal scales. The information contained in these maps summarizes key characteristics related with the physical environment and provides fundamental information of the Earth for vegetation monitoring or land use status over time. However, high spatial resolution land cover maps are usually only produced for specific small regions or in an image tile. We present a general methodology to obtain a high spatial resolution land cover maps using Landsat spectral information, the powerful Google Earth Engine platform, and operational coarse classification schemes such as the MODIS (MOD12) land cover. After the experimental analysis for different regions, we conclude that the method allows to successfully learn the MODIS Plant Functional Type classification scheme at 500 m pixel resolution which greatly improves the level of spatial detail when the machine learning model is applied to Landsat pixel resolution (30 m) reflectance data.

Original language	English
Pages	309-312
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9554790
State	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: Jul 12 2021 → Jul 16 2021

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	07/12/21 → 07/16/21

Funding

This research was financially supported by the NASA Earth Observing System MODIS project (grant NNX08AG87A) and the European Research Council (ERC) Consolidator Grant SEDAL (Statistical Learning for Earth Observation Data Analysis) project under Grant Agreement 647423.

Funders	Funder number
National Aeronautics and Space Administration	NNX08AG87A
647423

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 15 Life on Land

Keywords

Classification map
Google Earth Engine
High spatial resolution
Landsat
MODIS
Machine learning

Access to Document

10.1109/IGARSS47720.2021.9554790

Cite this

Izquierdo-Verdiguier, E., Moreno-Martínez, Á., Adsuara, J. E., Muñoz-Marí, J., Camps-Valls, G., Maneta, M. P., Kimball, J., Clinton, N., & Running, S. W. (2021). GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA. 309-312. Paper presented at 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium. https://doi.org/10.1109/IGARSS47720.2021.9554790

@conference{6079291e5d5048a9a74ed232e2aae65d,

title = "GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA",

abstract = "Image classification has become one of the most common applications in remote sensing yielding to the creation of a variety of operational thematic maps at multiple spatio-temporal scales. The information contained in these maps summarizes key characteristics related with the physical environment and provides fundamental information of the Earth for vegetation monitoring or land use status over time. However, high spatial resolution land cover maps are usually only produced for specific small regions or in an image tile. We present a general methodology to obtain a high spatial resolution land cover maps using Landsat spectral information, the powerful Google Earth Engine platform, and operational coarse classification schemes such as the MODIS (MOD12) land cover. After the experimental analysis for different regions, we conclude that the method allows to successfully learn the MODIS Plant Functional Type classification scheme at 500 m pixel resolution which greatly improves the level of spatial detail when the machine learning model is applied to Landsat pixel resolution (30 m) reflectance data.",

keywords = "Classification map, Google Earth Engine, High spatial resolution, Landsat, MODIS, Machine learning",

author = "Emma Izquierdo-Verdiguier and {\'A}lvaro Moreno-Mart{\'i}nez and Adsuara, \{Jose E.\} and Jordi Mu{\~n}oz-Mar{\'i} and Gustau Camps-Valls and Maneta, \{Marco P.\} and John Kimball and Nicholas Clinton and Running, \{Steven W.\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9554790",

language = "English",

pages = "309--312",

}

Izquierdo-Verdiguier, E, Moreno-Martínez, Á, Adsuara, JE, Muñoz-Marí, J, Camps-Valls, G, Maneta, MP, Kimball, J, Clinton, N & Running, SW 2021, 'GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA', Paper presented at 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 07/12/21 - 07/16/21 pp. 309-312. https://doi.org/10.1109/IGARSS47720.2021.9554790

TY - CONF

T1 - GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA

AU - Izquierdo-Verdiguier, Emma

AU - Moreno-Martínez, Álvaro

AU - Adsuara, Jose E.

AU - Muñoz-Marí, Jordi

AU - Camps-Valls, Gustau

AU - Maneta, Marco P.

AU - Kimball, John

AU - Clinton, Nicholas

AU - Running, Steven W.

PY - 2021

Y1 - 2021

N2 - Image classification has become one of the most common applications in remote sensing yielding to the creation of a variety of operational thematic maps at multiple spatio-temporal scales. The information contained in these maps summarizes key characteristics related with the physical environment and provides fundamental information of the Earth for vegetation monitoring or land use status over time. However, high spatial resolution land cover maps are usually only produced for specific small regions or in an image tile. We present a general methodology to obtain a high spatial resolution land cover maps using Landsat spectral information, the powerful Google Earth Engine platform, and operational coarse classification schemes such as the MODIS (MOD12) land cover. After the experimental analysis for different regions, we conclude that the method allows to successfully learn the MODIS Plant Functional Type classification scheme at 500 m pixel resolution which greatly improves the level of spatial detail when the machine learning model is applied to Landsat pixel resolution (30 m) reflectance data.

AB - Image classification has become one of the most common applications in remote sensing yielding to the creation of a variety of operational thematic maps at multiple spatio-temporal scales. The information contained in these maps summarizes key characteristics related with the physical environment and provides fundamental information of the Earth for vegetation monitoring or land use status over time. However, high spatial resolution land cover maps are usually only produced for specific small regions or in an image tile. We present a general methodology to obtain a high spatial resolution land cover maps using Landsat spectral information, the powerful Google Earth Engine platform, and operational coarse classification schemes such as the MODIS (MOD12) land cover. After the experimental analysis for different regions, we conclude that the method allows to successfully learn the MODIS Plant Functional Type classification scheme at 500 m pixel resolution which greatly improves the level of spatial detail when the machine learning model is applied to Landsat pixel resolution (30 m) reflectance data.

KW - Classification map

KW - Google Earth Engine

KW - High spatial resolution

KW - Landsat

KW - MODIS

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85129814004

U2 - 10.1109/IGARSS47720.2021.9554790

DO - 10.1109/IGARSS47720.2021.9554790

M3 - Paper

AN - SCOPUS:85129814004

SP - 309

EP - 312

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

GLOBAL UPSCALING OF THE MODIS LAND COVER WITH GOOGLE EARTH ENGINE AND LANDSAT DATA

Abstract

Conference

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this